AI AgentsOpt-in

Every agent action carries a name

Comments, reviews, commits and ticket updates made by an agent are stamped with which agent did them, in which run. The ledger shows one agent’s actions across every workflow, the audit answer to "who changed this?" when the who is a bot. Agents running outside e-volv can report their runs into the same ledger through the public API.

Opt in: requires the agents.identity flag

• Attribution on every PR comment, review, and commit trailer
• Per-agent ledger: runs, tool calls, tokens, and write actions
• Ed25519-signed identity tokens with scopes and a short TTL
• External agents ingest runs by external ID, same ledger, same page

1. Base agent typesSenior Developer, Code Reviewer, Tech Writer, Product Manager, and fully Custom agents.
2. Agent memoryPersistent memory tools let agents recall conventions, recurring issues, and decisions.
3. Multi-agent sessionsA coordinator delegates work across specialist agents and synthesizes the result.
4. MCP serversConnect remote MCP servers over streamable HTTP or SSE and their tools appear namespaced in every agent run.
5. Eval harnessOpt-inReplay any past step against a new prompt or model with write tools stripped, then diff what changed.